This investigation investigates the utilization of machine learning to optimize the precision and efficiency of bug assignment procedures. It underscores the importance of intelligent bug triaging in open-source software. Software repositories receive thousands of bug reports daily in extensive open-source projects. Manual sorting is largely ineffective, susceptible to errors, and laborious. The efficacy of machine learning algorithms, such as Naïve Bayes, Support Vector Machines (SVM), Random Forest, and deep learning models, in autonomously categorizing bug reports and directing them to appropriate developers based on historical bug data, textual descriptions, developer expertise, and project activity, is the focus of the proposed research. Informed predictions and prioritization are facilitated by the application of Natural Language Processing (NLP) methodologies to extract significant features from bug reports. The research aims to establish an automated and scalable bug triage framework in order to reduce the time required to rectify bugs, improve software quality, and increase developer productivity. Machine learning-based bug triaging significantly improves assignment accuracy and decreases the manual workload, as evidenced by tests conducted on real-world open-source datasets.